Merge branch 'dev_gzf_funasr2' into main

zhifu gao

2023-12-11 c0008fd46134d60a3a41b022bf9156cea5b145e5

 funasr/models/e2e_asr_paraformer.py

@@ -256,6 +256,7 @@
        # force_gatherable: to-device and to-tensor if scalar for DataParallel
        if self.length_normalized_loss:
            batch_size = int((text_lengths + self.predictor_bias).sum())

        loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
        return loss, stats, weight

@@ -868,6 +869,7 @@
        # force_gatherable: to-device and to-tensor if scalar for DataParallel
        if self.length_normalized_loss:
            batch_size = int((text_lengths + self.predictor_bias).sum())

        loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
        return loss, stats, weight

@@ -1495,6 +1497,7 @@
        # force_gatherable: to-device and to-tensor if scalar for DataParallel
        if self.length_normalized_loss:
            batch_size = int((text_lengths + self.predictor_bias).sum())

        loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
        return loss, stats, weight

@@ -1766,6 +1769,7 @@
        # force_gatherable: to-device and to-tensor if scalar for DataParallel
        if self.length_normalized_loss:
            batch_size = int((text_lengths + self.predictor_bias).sum())

        loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
        return loss, stats, weight

@@ -1968,6 +1972,7 @@
        # force_gatherable: to-device and to-tensor if scalar for DataParallel
        if self.length_normalized_loss:
            batch_size = int((text_lengths + self.predictor_bias).sum())

        loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
        return loss, stats, weight

@@ -2262,4 +2267,4 @@
                    "torch tensor: {}, {}, loading from tf tensor: {}, {}".format(name, data_tf.size(), name_tf,
                                                                                  var_dict_tf[name_tf].shape))

        return var_dict_torch_update
        return var_dict_torch_update